| View previous topic :: View next topic |
| Author |
Message |
Suer7reus Tux's lil' helper

Joined: 26 Nov 2003 Posts: 106
|
Posted: Sun Jan 08, 2006 2:41 am Post subject: Terrible Linux performance, great Win32 [SOLVED? - see post] |
|
|
I am having a terrible time with my Dell XPS (the first one) laptop. It works wonderfully in WinXP, except for the OS, but the Gentoo I've installed on it has never run right. I've set up my share of Gentoo boxes, and all are running smoothly except this. They all compile faster too, even the 4xPIII Xeon 500 Dell server compiling single-threaded. X is terribly sluggish, and my bashmark scores are all hefty negative percentages (vs a K7 1800+). I've taken it to my local LUG, and they agreed unanimously that I have a serious performance problem, but made no progress in correcting it. It takes over an hour to compile a kernel.
I suspect a kernel problem, I guess, but the problem is obvious on all of a) my 2.6.14-nitro2 (or the previous versions) fully preemptable, fully customized kernel, b) my tamer 2.6.14-gentoo-r* kernel, and c) my 2.6.12-gentoo kernel with absolutely nothing but filesystem drivers and IDE/block drivers, no preemption, all default options. I believe bootstrapping from the LiveCD was slow as well (it's been a while), and I have even thrown in a Knoppix (2.6 kernel) CD and compiled and run bashmark with totally fresh toolchain/libs, to no avail. My bashmark (integer) scores range from 200-1000 - they're consistent per the test conditions, but they change depending on whether or not I'm in X, in Knoppix, etc.
Here are my system specs:
P4 Prescott 3.4GHz, Hyperthreading
1Gb PC3200
256Mb Radeon 9800 AGP
For the record, I've tried:
Different kernels and configs, as described above
Every combination of {en|dis}abling HT is BIOS and kernel
Knoppix system
and I know DMA is turned on
What else can I possibly try? Help me! I really don't want to be stuck with this other dysfunctional OS all the time.
Thanks in advance!
Last edited by Suer7reus on Sun Jan 15, 2006 1:26 am; edited 1 time in total |
|
| Back to top |
|
 |
micmac l33t

Joined: 28 Nov 2003 Posts: 947
|
Posted: Sun Jan 08, 2006 3:27 am Post subject: |
|
|
| Can you post the ouput of 'emerge info'? |
|
| Back to top |
|
 |
Suer7reus Tux's lil' helper

Joined: 26 Nov 2003 Posts: 106
|
Posted: Sun Jan 08, 2006 12:58 pm Post subject: |
|
|
Here goes:
| Quote: | Portage 2.1_pre1 (default-linux/x86/2005.1, gcc-3.3.6, glibc-2.3.6-r1, 2.6.14-nitro2 i686)
=================================================================
System uname: 2.6.14-nitro2 i686 Intel(R) Pentium(R) 4 CPU 3.40GHz
Gentoo Base System version 1.12.0_pre11
distcc 2.18.3 i686-pc-linux-gnu (protocols 1 and 2) (default port 3632) [enabled]
dev-lang/python: 2.3.5, 2.4.2
sys-apps/sandbox: 1.2.17
sys-devel/autoconf: 2.13, 2.59-r7
sys-devel/automake: 1.4_p6, 1.5, 1.6.3, 1.7.9-r1, 1.8.5-r3, 1.9.6-r1
sys-devel/binutils: 2.16.1-r1
sys-devel/libtool: 1.5.20-r1
virtual/os-headers: 2.6.11-r3
ACCEPT_KEYWORDS="x86 ~x86"
AUTOCLEAN="yes"
CBUILD="i686-pc-linux-gnu"
CFLAGS="-O3 -march=prescott -pipe -fomit-frame-pointer -funroll-loops"
CHOST="i686-pc-linux-gnu"
CONFIG_PROTECT="/etc /opt/openjms/config /usr/kde/2/share/config /usr/kde/3.4/env /usr/kde/3.4/share/config /usr/kde/3.4/shutdown /usr/kde/3.5/env /usr/kde/3.5/share/config /usr/kde/3.5/shutdown /usr/kde/3/share/config /usr/lib/mozilla/defaults/pref /usr/share/X11/xkb /usr/share/config /var/bind /var/qmail/control"
CONFIG_PROTECT_MASK="/etc/gconf /etc/splash /etc/terminfo /etc/texmf/web2c /etc/env.d"
CXXFLAGS="-O3 -march=prescott -pipe -fomit-frame-pointer -funroll-loops"
DISTDIR="/usr/portage/distfiles"
FEATURES="autoconfig ccache distcc distlocks keeptemp keepwork sandbox sfperms strict"
GENTOO_MIRRORS="http://distfiles.gentoo.org http://distro.ibiblio.org/pub/linux/distributions/gentoo"
LC_ALL="en_US.UTF-8"
MAKEOPTS="-j1"
PKGDIR="/usr/portage/packages"
PORTAGE_TMPDIR="/var/tmp"
PORTDIR="/usr/portage"
PORTDIR_OVERLAY="/usr/local/portage /usr/local/gentopia /usr/local/bmg-main"
SYNC="rsync://rsync.suertreus.com/gentoo-portage/"
USE="x86 16bit 3ds 64bit 7zip S3TC X X509 Xaw3d a52 aac aalib abook accessibility accounting acl acpi activefilter ada adabas adns adsl aim aimextras aio aliaschain allegro alsa amarok amd amr amuled ansi anthy ao aotuv apache apache1 apache2 applet aqua_theme araneida ares artswrappersuid artworkextra aserve asm asterisk async athena atk atlas atm auctex audiofile authdaemond authfile automount avalon avantgo avi ax25 bahamut bash-completion batch bcmath bdf beep berkdb bgpclassless bidi bigpatch bind-mysql birdstep bitmap-fonts bl blas blender-game bluetooth bmp bonobo boo bootsplash bri brltty browserplugin buffysize buttons bzip2 c++ c3p0 cacheemu cairo calendar canna cap capi caps carbone_theme cardbus ccache cdb cdda cddb cdf cdio cdparanoia cdr cdrom cegui cg cgi chasen chroot cid cis cjk ck-plus clamav clamd clanJavaScript clanVoice cle266 clearcase cli clisp cln clock-screen cluster cmkopt cmucl cnamefix cobalt command-args commercial config_wizard corba courier cpdflib cpudetection cpulimit cracklib crosscompile crypt cscope css csv ctype cups curl curlwrappers custom-cflags customlog custreloc cvsgraph cyrus daap dar32 dar64 db2 dba dbase dbcp dbi dbm dbmaker dbus dbx debugger dedicated delays devfs26 devil devmap dga dhcp dict dillo dio directfb discard-path disk-cache distribution divx4linux djbfft djvu dlloader dlopen dlz dmalloc dmx dnd dnsdb double-precision dpms drac dri dtaus dts dv dvb dvd dvdr dvdread dvi dynagraph eb ecaggressive ecc ecmark ecmark2 ecmark3 ecsteve ecsteve2 edirectory editor edl eds effects elf emacs emacs-w3 emboss emoticon empress empress-bcs encode enscript epiphany epson erandom escreen esd esoob estraier esx ethereal etwin eurofile evo examples exif exim exiscan exiscan-acl expat experimental ext-iiimf ext-png ext-zlib extensions extraengine extraicons extramodules extras fakelog fam fame fastbuild fastcgi fat fax faxonly fbcon fbdev fbsplash fep festival ffcall ffmpeg fftw figlet filepro finger firebird firefox fits flac flash flatfile flexresp flood floppyd florz fltk fluidsynth fmod follow-xff font-server fontconfig foomaticdb force-cgi-redirect fortran fping fpx frascend freetds freetts freetype freewnn frontbase frxp ftp ftruncate fuse fwdzone gatos gb gcc-libffi gcj gcl gd gdal gdbm gecko-sdk geldkarte general geoip geometry geos gg ggi gif gimp gimpprint ginac gitsendemail gkrellm glade glep glgd glibc-compat20 glibc-omitfp glitz glut glx gmail gmailtimestamps gml gmp gmtfull gmthigh gmtsuppl gmttria gnokii gnome gnome-print gnomecanvas gnomedb gnuplot gnustep gnutls gopher gpgme gphoto2 gpm gprof gps graphicsmagick graphviz grass gs gsl gsm gsnd gssapi gstreamer gtk gtk2 guile gvim gzip h323 hal haskell hbci hddtemp hdf hdf5 hesiod hfs high-ints hlapi hou howl hpn html http httpd hub hyperwave-api icc icecast icon iconv icp icq icu id3 ide idea idl idled idn ieee1394 iksemel ilbc image imagemagick imap imlib imlib2 immqt-bc inetd informix ingres inifile inkjar inline innkeywords innodb inntaggedhash inode insecure-drivers insecure-savers interbase intl iodbc ipalias ipcs ipppd iproute2 ipv6 ipv6arpa irc irda irixpasswd irmc isdn isdnlog itcl ithreads j2ee jabber jack jack-tmpfs jai jasper java java-external java-internal javacomm javamail javascript jbig jboss jce jcs jfs jikes jimi jit jms jmx john joystick jp2 jpeg jpeg2k jpty jta jumpplay junit justify jython kadmos kakasi kcal kdeenablefinal kdepim kdexdeltas kdgraphics kerberos key-screen keyscrub kig-scripting kipi kjs kqemu krb4 ladcca ladspa lame lapack large-domain largenet largeterminal latex layout-from-conf-file layout-osx-like lcd lcms ldap ldapsam ldb ldirectord leim lesstif libabcl libcaca libclamav libdsk libedit libg++ libgda libsamplerate libtommath libvisual libwww lids lighttpd lingerd linuxkeys linuxthreads-tls lirc live lj lmtp lnbsharing log4j logitech-mouse logmail logrotate logwatch ltsp lua lynxkeymap lzo lzw m17n-lib mad madwifi mail mailbox maildir maildrop mailwrapper mapeditor maps math matroska maya-shaderlibrary mbox mbrola mcal mccp mcve md5sum mdb mecab mem-cache memcache memlimit menubar messages metar mew mgetty mhash migemo mikmod milter mime mimencode ming mixer mjpeg mmap mmx mmxext mng mnogosearch mod mod_irc mod_lisp mod_muc mod_pubsub mod_python mode-force mode-owner mode-paranoid modelock modperl moneyplex mono mopac7 motif mouse mozcalendar mozdevelop mozilla mozsvg mozxmlterm mp3 mp4live mpd-mad mpeg mpeg2 mpeg4 mpi mpm-peruser mppe-mppc mpqc mschap msdav msession mslu msn msnextras msql mssql muine mule multi-tty multicall multipleip multiprocess multislot multitarget mupad-noscilab musepack music musicbrainz mysql mysqli mzscheme nagios-dns nagios-game nagios-ntp nagios-ping nagios-ssh nas nautilus ncurses neXt net netbeans netboot netcdf nethack netpbm network neural nextaw nfs ngnet nis nls nntp nocd normalizemime nptl nsplugin nspr ntfs ntlm ntlm_unsupported_patch numarray numeric nvidea nvram oav objc ocaml oci8 octave odbc ode offensive ofx ogdi ogg oggvorbis ogre old-crypt old-eq on-the-fly-crypt openal openbabel openexr opengl openntpd openssh openssl oracle oracle7 orathreads ortp osc oscache oscar osp ospfapi oss overload ovrimos pam pam-mysql pam_chroot pam_console pam_timestamp pango parse-clocks pascal passfile patented pbs pcapnav pccts pci pcmcia pcntl pcre pda pdf pdfkit pdflib pdo-external pear perforce perl pfpro pg-hier pg-intdatetime pg-vacuumdelay pheaders php physfs pic pike player plotutils plugin plx pmu png pnp pop portaudio posix postfix postgres povray ppds pppd pregen prelude pri print priority procmail proj proxool pvm pwdb pxeserial pyste python qdbm qemu-fast qhull qmail quicktime quotas quotes radiotap radius rar rcu rdesktop readline real realms recode recursor reiserfs remix remote resperl rhino rhythmbox rle rogue roundrobin rpc rplay rpm rrdtool rsh rss rtc ruby samba sametime sapdb sasl savedconfig sbcl scp screen sdl search-screen semanticfix sendfile sendmail sensord serial server servlet-2.3 servlet-2.4 session seti sftp sftplogging sguil shape shaper shared sharedext sharedmem sheep shorten shout silc silvercity silverxp simplexml skey skk slang slp smime smp sms smtp smux sndfile snmp snortsam soap sockets socks5 softfax softmmu softquota solid sou sounds soundtouch sourcecaps sox spamassassin speech speedo speex spell spf spl sql sqlite sqlite3 srp srs srv sse sse-filters sse2 ssl standalone startup-notification staticsocket stats stencil-buffer stream streamzap stroke struts subject-rewrite subp subtitles subversion svg svga svgz swarmcache swat sybase sybase-ct sysfs syslog sysvipc szip t1lib tabs talkfilters tcltk tcp tcpd tcpmd5 tcsim tdb tetex text tga theora threads thumbnail tidy tiff timidity tlen tokenizer tomsfastmath toolbar tools tos transcode translator transparent-proxy truetype truetype-fonts trusted type1 type1-fonts ucs2 ucs4 udev udpfromto uim uml underscores unicode ups urandom usb utf8 uudeview v4l v4l2 vcd vcdimager vda verbose vfat vhosts videos vidix vim vim-pager vim-with-x virtual virtual-users virus-scan visualization vlm vmdbmysql vmdbpostgres vnc voice vorbis vpopmail watchdog wddx web webdav wifi win32codecs winbind withsamplescripts wma123 wmf wordexp wxgtk1 wxwindows x11vnc xanim xatrix xattr xbase xchatdccserver xchattext xemacs xerces-c xface xforms xfs xgetdefault xim xine xinerama xinetd xlockrc xmail xml xml2 xmlrpc xmms xosd xpm xprint xrandr xscreensaver xsl xslt xv xvid xvmc yahoo yaz yp yv12 zapnet zapras zaptel zeo zero-penalty-hit zeroconf zip zlib zvbi elibc_glibc kernel_linux userland_GNU"
Unset: ASFLAGS, CTARGET, LANG, LDFLAGS, LINGUAS |
Notes:
I have not compiled anything with march=prescott - I just switched it over from pentium4
I really don't think any of this has much bearing on the problem, as none of the packages on the Knoppix system I benchmarked on were compiled with these settings, or portage at all. As I said, that benchmark gave the same terrible results I have always gotten in Linux.
Thanks! |
|
| Back to top |
|
 |
sirdilznik l33t


Joined: 28 Apr 2005 Posts: 731
|
Posted: Sun Jan 08, 2006 1:39 pm Post subject: |
|
|
| Holy USE flag overkill, Batman!!!!!!!! |
|
| Back to top |
|
 |
Voltago Veteran


Joined: 02 Sep 2003 Posts: 2237 Location: Hinter den Materiequellen
|
Posted: Sun Jan 08, 2006 2:05 pm Post subject: |
|
|
Perhaps you should turn off a USE flag or two... Also, look for Inspiron XPS entries in this list:
http://tuxmobil.org/dell.html
they might help you to configure your system. |
|
| Back to top |
|
 |
hazza n00b


Joined: 30 Dec 2002 Posts: 53 Location: Burton on Trent
|
Posted: Sun Jan 08, 2006 2:27 pm Post subject: |
|
|
Just a quick thought: is SpeedStep getting in the way? I have an XPS M140 and it seems to like running at 600MHz unless you ask it nicely
Try the following: | Code: | # emerge cpufrequtils
# cpufreq-info
cpufrequtils 0.4: cpufreq-info (C) Dominik Brodowski 2004
Report errors and bugs to linux@brodo.de, please.
analyzing CPU 0:
driver: centrino
CPUs which need to switch frequency at the same time: 0
hardware limits: 600 MHz - 1.70 GHz
available frequency steps: 1.70 GHz, 1.40 GHz, 1.20 GHz, 1000 MHz, 800 MHz, 600 MHz
available cpufreq governors: conservative, ondemand, powersave, userspace
current policy: frequency should be within 600 MHz and 1.70 GHz.
The governor "ondemand" may decide which speed to use
within this range.
current CPU frequency is 1.70 GHz (asserted by call to hardware). | Check the last line and see what speed your CPU is running at. There is an option in my XPS BIOS to nail the processor down at its lowest speed, also. While cpufrequtils utils seem to be able to override this, it can only do this assuming you have CPU throttling support in your kernel.
The Gentoo Power Management guide goes through this in great detail!
Cheers,
--Harry |
|
| Back to top |
|
 |
hazza n00b


Joined: 30 Dec 2002 Posts: 53 Location: Burton on Trent
|
Posted: Sun Jan 08, 2006 2:30 pm Post subject: |
|
|
Another thought: you can check CPU frequency without any tools by displaying the contents of /proc/cpuinfo: | Code: | # cat /proc/cpuinfo
processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 13
model name : Intel(R) Pentium(R) M processor 1.70GHz
stepping : 8
cpu MHz : 1696.072
cache size : 2048 KB
fdiv_bug : no
hlt_bug : no
f00f_bug : no
coma_bug : no
fpu : yes
fpu_exception : yes
cpuid level : 2
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat clflush dts acpi mmx fxsr sse sse2 ss tm pbe nx est tm2
bogomips : 3396.55 | cpu MHz line is the interesting bit!
Cheers,
--Harry |
|
| Back to top |
|
 |
Suer7reus Tux's lil' helper

Joined: 26 Nov 2003 Posts: 106
|
Posted: Mon Jan 09, 2006 10:57 pm Post subject: |
|
|
Thank you very much for your replies! I shall address them in order:
USE flags - although I have a lot turned on, most of them are local flags, and most of those affect packages I don't even have installed. I have an even more USE-intensive system running on my server, which performs very, very well. I use a lot of the packages the global flags are for, eg apache, mysql, pgsql, etc, but only rarely. I use the machine as an ordinary laptop most of the time, but the kernel has modular support for lots of miscellaneous things so I can turn it into a router in a pinch, for example. I don't run too many services at boot, and top'ping the system shows those I do use are unobtrusive. In any case, the fact that my problem presists even outside the Gentoo system (i.e. the Knoppix I booted and benchmarked under) tells me that USE flags, while they may be a small factor, are not the principal one.
IXPS tuxmobil.org link - Thanks, but I have already done all of the things listed. Gentoo's makes it mighty easy.
I'm fairly familiar with both CPU scaling interfaces - the old ACPI throttling as well as SpeedStep / cpufreq. I am pretty sure that these are not at fault. My CPU is listed in /proc/cpuinfo, cpufreq-info, and the /proc interface to cpufreq as running at full speed. I can change governors and speeds and everything, but I have the system default to the performance governor (i.e. cranked all the way up). I can read the ACPI state from /proc as 0% (throttled down by 0%, i.e. full speed), and I can change it for an extra burst of slowness if I'm so inclined.
Thanks a lot for your input and your time, but my issue remains unresolved. |
|
| Back to top |
|
 |
falcon_za Tux's lil' helper


Joined: 31 Aug 2004 Posts: 136 Location: Nara - Japan
|
Posted: Mon Jan 09, 2006 11:21 pm Post subject: |
|
|
I also suggest you try to go easy on the useflags.
I think that you could go for -O2 instead of -O3. 3 is supposed to make stronger optimization than 2, but it also usualy results in larger files. On a laptop, which has limited hard drive performance, and possibly limited caches size and memory bandwidth, I think It might actualy result in slower performance. As for as the -funroll-loops, the situation might have changed without my knowing, but it used to be a broken flag, best avoided.
All that said, if other distro have proven sluggish too, it is likely unrelated to the way you configured your box, but if I were you, I'd still try to go with a slightly more conventional config. _________________ Why the hell am I in Asia? Don't remember. But I am still glad i am here.
You're glad someone did it for you, so help noobs. |
|
| Back to top |
|
 |
hazza n00b


Joined: 30 Dec 2002 Posts: 53 Location: Burton on Trent
|
Posted: Tue Jan 10, 2006 5:25 am Post subject: |
|
|
| Quote: | | ...as none of the packages on the Knoppix system I benchmarked on were compiled with these settings, or portage at all. As I said, that benchmark gave the same terrible results I have always gotten in Linux. | My next thought is that there is something moderately odd about your system, perhaps a new iteration of Intel's integrated controller hub or something that is just getting in the way. I'm sure you'll have checked this already, but any chance you can post (or post a link to) the output of dmesg after boot and also the output of lspci -v.
Cheers,
--Harry |
|
| Back to top |
|
 |
Pse Apprentice

Joined: 01 Mar 2005 Posts: 188 Location: by the plate river
|
Posted: Tue Jan 10, 2006 5:24 pm Post subject: |
|
|
| What kind of hardware is there in your machine? (apart from your graphics card, CPU and memories?) |
|
| Back to top |
|
 |
saber850 Tux's lil' helper


Joined: 21 Mar 2004 Posts: 103
|
Posted: Tue Jan 10, 2006 6:32 pm Post subject: |
|
|
One significant performance problem I've had was caused by no DMA on the hard disk.
Aside from DMA, there's a slew of other params that affect your HD performance.
Use hdparm to check your config and tweak as necessary. |
|
| Back to top |
|
 |
Suer7reus Tux's lil' helper

Joined: 26 Nov 2003 Posts: 106
|
Posted: Thu Jan 12, 2006 1:04 am Post subject: |
|
|
Thank you all again for your replies!
Prepare yourselves for the mother of all posts, heh.
I shall address them in order again:
USE flags - not to be changed in pursuit of a solution to this problem as the problem presists even in non-Gentoo Linux systems (i.e. Knoppix).
CFLAGS - also should not affect the Knoppix system. My laptop is designed to be a gaming platform and therefore has a 7200RPM UDMA5 disk drive as well as plenty of cache and memory bandwidth. Therefore, I don't think -O* should make a big difference, and I'm certain it should not make the difference the below bashmark results demonstrate. -funroll-loops works just fine on all my other boxes, and has for quite some time, and as such I am inclined to trust it.
Regarding the above, I have considered changing some flags, but intend to deal with the matter once this problem is resolved and the machine can [re]compile code fast enough to be worth my bother.
Obscure hardware - I actually have not checked my hardware out much at all - upon install it sounded simple enough and appeared to be well-supported in the kernel, but I can't help but think you're barking up the right tree now in light of my troubles.
Here's dmesg right after boot of my absolute bare-bones compiled-just-for-this-test 2.6.12 kernel:
| Code: | Linux version 2.6.12-gentoo-r10 (root@cthulhu) (gcc version 3.3.6 (Gentoo 3.3.6, ssp-3.3.6-1.0, pie-8.7.8)) #3 Tue Jan 3 18:40:20 UTC 2006
BIOS-provided physical RAM map:
BIOS-e820: 0000000000000000 - 000000000009f000 (usable)
BIOS-e820: 000000000009f000 - 00000000000a0000 (reserved)
BIOS-e820: 0000000000100000 - 000000003ffaa800 (usable)
BIOS-e820: 000000003ffaa800 - 0000000040000000 (reserved)
BIOS-e820: 00000000fec00000 - 00000000fec10000 (reserved)
BIOS-e820: 00000000fecf0000 - 00000000fecf1000 (reserved)
BIOS-e820: 00000000fed20000 - 00000000fed90000 (reserved)
BIOS-e820: 00000000feda0000 - 00000000fee10000 (reserved)
BIOS-e820: 00000000ffb00000 - 0000000100000000 (reserved)
Warning only 896MB will be used.
Use a HIGHMEM enabled kernel.
896MB LOWMEM available.
On node 0 totalpages: 229376
DMA zone: 4096 pages, LIFO batch:1
Normal zone: 225280 pages, LIFO batch:31
HighMem zone: 0 pages, LIFO batch:1
DMI 2.3 present.
Allocating PCI resources starting at 40000000 (gap: 40000000:bec00000)
Built 1 zonelists
Kernel command line: BOOT_IMAGE=Gentoo*Test ro root=302 udev nodevfs
Initializing CPU#0
PID hash table entries: 4096 (order: 12, 65536 bytes)
Detected 3392.806 MHz processor.
Using tsc for high-res timesource
Console: colour VGA+ 80x25
Dentry cache hash table entries: 131072 (order: 7, 524288 bytes)
Inode-cache hash table entries: 65536 (order: 6, 262144 bytes)
Memory: 907416k/917504k available (1107k kernel code, 9632k reserved, 288k data, 100k init, 0k highmem)
Checking if this processor honours the WP bit even in supervisor mode... Ok.
Calibrating delay loop... 6684.67 BogoMIPS (lpj=3342336)
Mount-cache hash table entries: 512
CPU: After generic identify, caps: bfebfbff 00000000 00000000 00000000 0000441d 00000000 00000000
CPU: After vendor identify, caps: bfebfbff 00000000 00000000 00000000 0000441d 00000000 00000000
monitor/mwait feature present.
using mwait in idle threads.
CPU: Trace cache: 12K uops, L1 D cache: 16K
CPU: L2 cache: 1024K
CPU: After all inits, caps: bfebfbff 00000000 00000000 00000080 0000441d 00000000 00000000
CPU: Intel(R) Pentium(R) 4 CPU 3.40GHz stepping 04
Enabling fast FPU save and restore... done.
Enabling unmasked SIMD FPU exception support... done.
Checking 'hlt' instruction... OK.
Linux NoNET1.0 for Linux 2.6
PCI: PCI BIOS revision 2.10 entry at 0xfcc7e, last bus=2
PCI: Using configuration type 1
PCI: Probing PCI hardware
PCI: Probing PCI hardware (bus 00)
PCI: Ignoring BAR0-3 of IDE controller 0000:00:1f.1
Boot video device is 0000:01:00.0
PCI: Transparent bridge - 0000:00:1e.0
PCI: Discovered primary peer bus 08 [IRQ]
PCI: Using IRQ router PIIX/ICH [8086/24d0] at 0000:00:1f.0
PCI: IRQ 0 for device 0000:00:1f.1 doesn't match PIRQ mask - try pci=usepirqmask
PCI: Found IRQ 11 for device 0000:00:1f.1
PCI: Sharing IRQ 11 with 0000:00:1d.2
PCI: Sharing IRQ 11 with 0000:02:00.0
serio: i8042 AUX port at 0x60,0x64 irq 12
serio: i8042 KBD port at 0x60,0x64 irq 1
mice: PS/2 mouse device common for all mice
io scheduler noop registered
io scheduler deadline registered
Uniform Multi-Platform E-IDE driver Revision: 7.00alpha2
ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
ICH5: IDE controller at PCI slot 0000:00:1f.1
PCI: Enabling device 0000:00:1f.1 (0005 -> 0007)
PCI: Found IRQ 11 for device 0000:00:1f.1
PCI: Sharing IRQ 11 with 0000:00:1d.2
PCI: Sharing IRQ 11 with 0000:02:00.0
ICH5: chipset revision 2
ICH5: not 100% native mode: will probe irqs later
ide0: BM-DMA at 0xbfa0-0xbfa7, BIOS settings: hda:DMA, hdb:pio
ide1: BM-DMA at 0xbfa8-0xbfaf, BIOS settings: hdc:DMA, hdd:pio
Probing IDE interface ide0...
input: AT Translated Set 2 keyboard on isa0060/serio0
hda: FUJITSU MHT2060AH, ATA DISK drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
Probing IDE interface ide1...
hdc: HL-DT-STCD-RW/DVD-ROM GCC-4243N, ATAPI CD/DVD-ROM drive
ide1 at 0x170-0x177,0x376 on irq 15
Probing IDE interface ide2...
Probing IDE interface ide3...
Probing IDE interface ide4...
Probing IDE interface ide5...
hda: max request size: 128KiB
hda: 117210240 sectors (60011 MB) w/8192KiB Cache, CHS=65535/16/63, UDMA(100)
hda: cache flushes supported
hda: hda1 hda2 hda3 hda4 < hda5 hda6 >
ReiserFS: hda2: found reiserfs format "3.6" with standard journal
ReiserFS: hda2: using ordered data mode
ReiserFS: hda2: journal params: device hda2, size 8192, journal first block 18, max trans len 1024, max batch 900, max commit age 30, max trans age 30
ReiserFS: hda2: checking transaction log (hda2)
ReiserFS: hda2: Using r5 hash to sort names
VFS: Mounted root (reiserfs filesystem) readonly.
Freeing unused kernel memory: 100k freed |
Here is some hot lspci -v action:
| Code: | 00:00.0 Host bridge: Intel Corporation 82865G/PE/P DRAM Controller/Host-Hub Interface (rev 02)
Subsystem: Dell Unknown device 017c
Flags: bus master, fast devsel, latency 0
Memory at f0000000 (32-bit, prefetchable) [size=128M]
Capabilities: [e4] Vendor Specific Information
Capabilities: [a0] AGP version 3.0
00:01.0 PCI bridge: Intel Corporation 82865G/PE/P PCI to AGP Controller (rev 02) (prog-if 00 [Normal decode])
Flags: bus master, 66MHz, fast devsel, latency 32
Bus: primary=00, secondary=01, subordinate=01, sec-latency=32
I/O behind bridge: 0000c000-0000cfff
Memory behind bridge: fc000000-fdffffff
Prefetchable memory behind bridge: e0000000-efffffff
00:1d.0 USB Controller: Intel Corporation 82801EB/ER (ICH5/ICH5R) USB UHCI Controller #1 (rev 02) (prog-if 00 [UHCI])
Subsystem: Dell Unknown device 017c
Flags: bus master, medium devsel, latency 0, IRQ 17
I/O ports at bf80 [size=32]
00:1d.1 USB Controller: Intel Corporation 82801EB/ER (ICH5/ICH5R) USB UHCI Controller #2 (rev 02) (prog-if 00 [UHCI])
Subsystem: Dell Unknown device 017c
Flags: bus master, medium devsel, latency 0, IRQ 16
I/O ports at bf60 [size=32]
00:1d.2 USB Controller: Intel Corporation 82801EB/ER (ICH5/ICH5R) USB UHCI Controller #3 (rev 02) (prog-if 00 [UHCI])
Subsystem: Dell Unknown device 017c
Flags: bus master, medium devsel, latency 0, IRQ 19
I/O ports at bf40 [size=32]
00:1d.3 USB Controller: Intel Corporation 82801EB/ER (ICH5/ICH5R) USB UHCI Controller #4 (rev 02) (prog-if 00 [UHCI])
Subsystem: Dell Unknown device 017c
Flags: bus master, medium devsel, latency 0, IRQ 17
I/O ports at bf20 [size=32]
00:1d.7 USB Controller: Intel Corporation 82801EB/ER (ICH5/ICH5R) USB2 EHCI Controller (rev 02) (prog-if 20 [EHCI])
Subsystem: Dell Unknown device 017c
Flags: bus master, medium devsel, latency 0, IRQ 20
Memory at f8fffc00 (32-bit, non-prefetchable) [size=1K]
Capabilities: [50] Power Management version 2
Capabilities: [58] Debug port
00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev c2) (prog-if 00 [Normal decode])
Flags: bus master, fast devsel, latency 0
Bus: primary=00, secondary=02, subordinate=02, sec-latency=32
I/O behind bridge: 0000e000-0000efff
Memory behind bridge: fa000000-fbffffff
Prefetchable memory behind bridge: 50000000-52ffffff
00:1f.0 ISA bridge: Intel Corporation 82801EB/ER (ICH5/ICH5R) LPC Interface Bridge (rev 02)
Flags: bus master, medium devsel, latency 0
00:1f.1 IDE interface: Intel Corporation 82801EB/ER (ICH5/ICH5R) IDE Controller (rev 02) (prog-if 8a [Master SecP PriP])
Subsystem: Dell Unknown device 017c
Flags: bus master, medium devsel, latency 0, IRQ 17
I/O ports at <ignored>
I/O ports at <ignored>
I/O ports at <ignored>
I/O ports at <ignored>
I/O ports at bfa0 [size=16]
Memory at 53000000 (32-bit, non-prefetchable) [size=1K]
00:1f.5 Multimedia audio controller: Intel Corporation 82801EB/ER (ICH5/ICH5R) AC'97 Audio Controller (rev 02)
Subsystem: Dell Unknown device 017c
Flags: bus master, medium devsel, latency 0, IRQ 18
I/O ports at d800 [size=256]
I/O ports at dc40 [size=64]
Memory at f8fff800 (32-bit, non-prefetchable) [size=512]
Memory at f8fff400 (32-bit, non-prefetchable) [size=256]
Capabilities: [50] Power Management version 2
00:1f.6 Modem: Intel Corporation 82801EB/ER (ICH5/ICH5R) AC'97 Modem Controller (rev 02) (prog-if 00 [Generic])
Subsystem: Conexant Unknown device 5422
Flags: bus master, medium devsel, latency 0, IRQ 18
I/O ports at d400 [size=256]
I/O ports at d080 [size=128]
Capabilities: [50] Power Management version 2
01:00.0 VGA compatible controller: ATI Technologies Inc M18 JN [Radeon Mobility 9800] (prog-if 00 [VGA])
Subsystem: Dell Unknown device 5106
Flags: bus master, VGA palette snoop, 66MHz, medium devsel, latency 32, IRQ 11
Memory at e0000000 (32-bit, prefetchable) [size=256M]
I/O ports at c000 [size=256]
Memory at fcff0000 (32-bit, non-prefetchable) [size=64K]
Expansion ROM at fc000000 [disabled] [size=128K]
Capabilities: [58] AGP version 3.0
Capabilities: [50] Power Management version 2
02:00.0 Ethernet controller: Broadcom Corporation NetXtreme BCM5705M Gigabit Ethernet (rev 01)
Subsystem: Dell Latitude D400
Flags: bus master, 66MHz, medium devsel, latency 32, IRQ 19
Memory at faff0000 (64-bit, non-prefetchable) [size=64K]
Expansion ROM at 52000000 [disabled] [size=64K]
Capabilities: [48] Power Management version 2
Capabilities: [50] Vital Product Data
Capabilities: [58] Message Signalled Interrupts: 64bit+ Queue=0/3 Enable-
02:01.0 CardBus bridge: Texas Instruments PCI4510 PC card Cardbus Controller (rev 02)
Subsystem: Dell Unknown device 017c
Flags: bus master, medium devsel, latency 168, IRQ 16
Memory at fa000000 (32-bit, non-prefetchable) [size=4K]
Bus: primary=02, secondary=03, subordinate=06, sec-latency=176
Memory window 0: 50000000-51fff000 (prefetchable)
Memory window 1: 54000000-55fff000
I/O window 0: 0000e000-0000e0ff
I/O window 1: 0000e400-0000e4ff
16-bit legacy interface ports at 0001
02:01.1 FireWire (IEEE 1394): Texas Instruments PCI4510 IEEE-1394 Controller (prog-if 10 [OHCI])
Subsystem: Dell Unknown device 017c
Flags: bus master, medium devsel, latency 32, IRQ 11
Memory at fafef800 (32-bit, non-prefetchable) [size=2K]
Memory at fafe8000 (32-bit, non-prefetchable) [size=16K]
Capabilities: [44] Power Management version 2
02:03.0 Network controller: Broadcom Corporation BCM4309 802.11a/b/g (rev 03)
Subsystem: Dell Truemobile 1450 MiniPCI
Flags: bus master, fast devsel, latency 32, IRQ 18
Memory at fafec000 (32-bit, non-prefetchable) [size=8K] |
And here, for your reading pleasure, is the bashmark I ran immediately after that dmesg:
| Code: | #######################################################
: T E S T : :S C O R E : : R A T I O:
:-----------------------------------------------------:
:Cpu, Integer : : 1164: : +8%:
:Cpu, Floating point : : 14: : -98%:
: : : : : :
:Memory r/w (cached) : : 1747: : +45%:
:Memory de-/alloc : : 259: : -60%:
: : : : : :
:Multithreading : : 701: : -72%:
#######################################################
: S Y S T E M I N F O :
-------------------------------------------------------
1x Intel(R) Pentium(R) 4 3392.806MHz, L2 1024KB
Linux 2.6.12-gentoo-r10
GCC 3.3.6
112KB binary size
#######################################################
: R E F E R E N C E S Y S T E M I N F O :
-------------------------------------------------------
Reference system was Geno's pc with:
Athlon XP 1800+ 1575.631MHz, 256KB
Linux 2.6.11-ck1
GCC 3.4.3-20050110 (compiled with standard cflags)
glibc 2.3.4 (with nptl)
128KB binary size
Scores gathered on March, 30th. 2005 with bashmark 0.6 |
But what list of numbers would be complete without /proc/cpuinfo? None, say I:
| Code: | processor : 0
vendor_id : GenuineIntel
cpu family : 15
model : 3
model name : Intel(R) Pentium(R) 4 CPU 3.40GHz
stepping : 4
cpu MHz : 3392.806
cache size : 1024 KB
fdiv_bug : no
hlt_bug : no
f00f_bug : no
coma_bug : no
fpu : yes
fpu_exception : yes
cpuid level : 5
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe pni monitor ds_cpl cid xtpr
bogomips : 6684.67 |
All of these except the lspci (taken from a kernel with a PCI device name database) were taken immediately after boot of my 2.6.12 bare-bones kernel. I ^C'd init, so of course there was no X in the picture nor any other services / nonsense.
Hardware - the highlights from the above lspci include standard notebook chipsets with IEEE1394, USB, sound, bcm570x / tg3 gigabit netcard, and an ndiswrapper'd (when I use the other kernel) Broadcom/Dell MiniPCI wlan card.
DMA - I'm quite sure that DMA is turned on, and I'm pretty happy with the rest of my hdparm settings. Furthermore, as bashmark ought to run entirely from cache I'm not overly concerned with disk performance.
Thank you once more for your time. I am still very much puzzling over my issue, but have sort of run out of ideas. If there are any other files you would like, please let me know and I shall post them ASAP. |
|
| Back to top |
|
 |
hansmaa n00b

Joined: 11 Feb 2005 Posts: 65
|
Posted: Thu Jan 12, 2006 4:08 am Post subject: |
|
|
I don't know if this might help, but have you tried passing the 'irqpoll' option to the kernel from the bootloader??
You might have some none-fatal irq conflicts that slows your system down... |
|
| Back to top |
|
 |
MaGuS Guru


Joined: 13 Jun 2002 Posts: 302 Location: Luebeck, Germany
|
Posted: Thu Jan 12, 2006 4:16 am Post subject: |
|
|
Hi,
did you tried to turn off preemptable? On one box i got the same problem, after turning off preemptable the system is running much better!
Best regards,
Magnus _________________ Running Gentoo as:
htpc with vdr and many plugins (DVB-S and DVB-T) on an AMD Athlon(tm) XP 2600+
router with shorewall on an apple mac mini
web and e-mail server on a dell (root server) |
|
| Back to top |
|
 |
cyanide_nfs n00b

Joined: 16 Dec 2005 Posts: 22
|
Posted: Thu Jan 12, 2006 10:55 am Post subject: |
|
|
well, i didnt mean to rub it in or anything, but your bashmark results seem kinda low...
heres my results with a a64 2800+ with 512mb ddr400 ram:
| Quote: | #######################################################
: T E S T : :S C O R E : : R A T I O:
:-----------------------------------------------------:
:Cpu, Integer : : 1310: : +22%:
:Cpu, Floating point : : 1224: : +61%:
: : : : : :
:Memory r/w (cached) : : 10005: : +732%:
:Memory de-/alloc : : 656: : +0%:
: : : : : :
:Multithreading : : 2187: : -12%:
#######################################################
: S Y S T E M I N F O :
-------------------------------------------------------
1x AMD Athlon(tm) 64 2800+ 1808.824MHz, L2 512KB
Linux 2.6.14-gentoo-r5
GCC 3.4.4
108KB binary size
#######################################################
: R E F E R E N C E S Y S T E M I N F O :
-------------------------------------------------------
Reference system was Geno's pc with:
Athlon XP 1800+ 1575.631MHz, 256KB
Linux 2.6.11-ck1
GCC 3.4.3-20050110 (compiled with standard cflags)
glibc 2.3.4 (with nptl)
128KB binary size
Scores gathered on March, 30th. 2005 with bashmark 0.6
|
|
|
| Back to top |
|
 |
Suer7reus Tux's lil' helper

Joined: 26 Nov 2003 Posts: 106
|
Posted: Thu Jan 12, 2006 2:35 pm Post subject: |
|
|
Thank you again!
irqpoll - I shall try this as soon as I return to the computer this afternoon - this is the kind of suggestion I was hoping for. Thank you!
preemptable - I have tried both preemptable and non-preemptable kernels. Neither performs correctly. Good suggestion though; preemption seems like the kind of change that could so affect performance in certain circumstances, just not mine apparently.
bashmark - Agreed! I wonder if my preposterously low floating point scores are at all indicative of the true cause of my problem. What that cause might be, I don't know, I'm just thinking out loud.
Thanks again; update tonight! |
|
| Back to top |
|
 |
hansmaa n00b

Joined: 11 Feb 2005 Posts: 65
|
Posted: Thu Jan 12, 2006 3:49 pm Post subject: |
|
|
Also try to add 'pci=usepirqmask' option to the kernel from the bootloader. Your dmesg complains about it.
Also, dmesg shows some unwillingness to lock on to what kind of cpu you have. (At least to me, being an AMD user)
Have you compiled your kernel for a different cpu than you are running it on?? |
|
| Back to top |
|
 |
linuxtuxhellsinki l33t


Joined: 15 Nov 2004 Posts: 668 Location: Hellsinki
|
Posted: Thu Jan 12, 2006 5:04 pm Post subject: |
|
|
I'll give you this from my ThinkPad, just for fun
| Code: | hellsinki ~ # bashmark
#######################################################
: T E S T : :S C O R E : : R A T I O:
:-----------------------------------------------------:
:Cpu, Integer : : 190: : -82%:
:Cpu, Floating point : : 14: : -98%:
: : : : : :
:Memory r/w (cached) : : 162: : -87%:
:Memory de-/alloc : : 85: : -87%:
: : : : : :
:Multithreading : : 252: : -90%:
#######################################################
: S Y S T E M I N F O :
-------------------------------------------------------
1x Pentium II (Deschutes) 298.508MHz, L2 512KB
Linux 2.6.14-gentoo-r2-600
GCC 3.4.4
104KB binary size
#######################################################
: R E F E R E N C E S Y S T E M I N F O :
-------------------------------------------------------
Reference system was Geno's pc with:
Athlon XP 1800+ 1575.631MHz, 256KB
Linux 2.6.11-ck1
GCC 3.4.3-20050110 (compiled with standard cflags)
glibc 2.3.4 (with nptl)
128KB binary size
Scores gathered on March, 30th. 2005 with bashmark 0.6 |
_________________ 1st use 'Search' & lastly
add [SOLVED] to subject  |
|
| Back to top |
|
 |
GNUtoo Veteran


Joined: 05 May 2005 Posts: 1919
|
Posted: Thu Jan 12, 2006 7:32 pm Post subject: |
|
|
| sirdilznik wrote: | | Holy USE flag overkill, Batman!!!!!!!! |
lol
use="*" ??? (traduction: is he trying to use evrything...)
personaly i :
emerge -pv package
then i choose the flags
then nano /etc/make.conf
then emerge -pv (check)
then emerge
but what he does takes less (human) time
mabe the cpu is too hot? |
|
| Back to top |
|
 |
Felixlein n00b

Joined: 26 Oct 2005 Posts: 28
|
Posted: Thu Jan 12, 2006 8:42 pm Post subject: |
|
|
Why is nearly everybody complaining about use-flags?
I dont think they have anything to do with the poor guys
about-zero-floating-point-performance... |
|
| Back to top |
|
 |
Felixlein n00b

Joined: 26 Oct 2005 Posts: 28
|
Posted: Thu Jan 12, 2006 8:51 pm Post subject: |
|
|
Hmm,I also have this bad fpu-performance,listening to bashmark;
didn't recognize it until now...
samuelcolt felixlein # bashmark
#######################################################
: T E S T : :S C O R E : : R A T I O:
:-----------------------------------------------------:
:Cpu, Integer : : 914: : -15%:
:Cpu, Floating point : : 21: : -97%:
: : : : : :
:Memory r/w (cached) : : 645: : -46%:
:Memory de-/alloc : : 233: : -64%:
: : : : : :
:Multithreading : : 686: : -72%:
#######################################################
: S Y S T E M I N F O :
-------------------------------------------------------
2x Intel(R) Pentium(R) 4 3065.563MHz, L2 512KB
Linux 2.6.15-gentoo
GCC 4.1.0-beta20060106
88KB binary size
####################################################### |
|
| Back to top |
|
 |
GNUtoo Veteran


Joined: 05 May 2005 Posts: 1919
|
Posted: Thu Jan 12, 2006 8:56 pm Post subject: |
|
|
is the cpu trotelling???
cat /proc/acpi/processor/CPU0/throttling
if it's not to 00 it's trotelling
check it when you do your benchhmark
mabe also try remplacing your root by a stage3 and run the test for showing that it's not the use flags (how this could be possible...it just make run the program heavyer...not the system so slow)
#######################################################
: T E S T : :S C O R E : : R A T I O:
:-----------------------------------------------------:
:Cpu, Integer : : 420: : -61%:
:Cpu, Floating point : : 33: : -96%:
: : : : : :
:Memory r/w (cached) : : 920: : -24%:
:Memory de-/alloc : : 118: : -82%:
: : : : : :
:Multithreading : : 397: : -84%:
#######################################################
: S Y S T E M I N F O :
-------------------------------------------------------
1x Pentium III (Coppermine) 697.946MHz, L2 256KB
Linux 2.6.14-gentoo-r2_dell_inspiron2500
GCC 3.3.5-20050130
100KB binary size
while running some kde,konqueror(a lot of instances),xconfig,firefox(a lot of tabs),xterm(a lot of instances)
try it under windows
what is the result? |
|
| Back to top |
|
 |
cyanide_nfs n00b

Joined: 16 Dec 2005 Posts: 22
|
Posted: Thu Jan 12, 2006 11:35 pm Post subject: |
|
|
| is it just me or are the pentiums really bad in the benchmarks ? |
|
| Back to top |
|
 |
GNUtoo Veteran


Joined: 05 May 2005 Posts: 1919
|
Posted: Fri Jan 13, 2006 12:33 am Post subject: |
|
|
| it's said on the faq that the "intel processors" are bad at this benchmark |
|
| Back to top |
|
 |
|
|
You cannot post new topics in this forum You cannot reply to topics in this forum You cannot edit your posts in this forum You cannot delete your posts in this forum You cannot vote in polls in this forum
|
|